Commit d8ea7cc8 authored by Zach O'Keefe's avatar Zach O'Keefe Committed by Andrew Morton
Browse files

mm/khugepaged: add flag to predicate khugepaged-only behavior 

Add .is_khugepaged flag to struct collapse_control so khugepaged-specific
behavior can be elided by MADV_COLLAPSE context.

Start by protecting khugepaged-specific heuristics by this flag.  In
MADV_COLLAPSE, the user presumably has reason to believe the collapse will
be beneficial and khugepaged heuristics shouldn't prevent the user from
doing so:

1) sysfs-controlled knobs khugepaged_max_ptes_[none|swap|shared]

2) requirement that some pages in region being collapsed be young or
   referenced

[zokeefe@google.com: consistently order cc->is_khugepaged and pte_* checks]
  Link: https://lkml.kernel.org/r/20220720140603.1958773-3-zokeefe@google.com
  Link: https://lore.kernel.org/linux-mm/Ys2qJm6FaOQcxkha@google.com/
Link: https://lkml.kernel.org/r/20220706235936.2197195-7-zokeefe@google.com


Signed-off-by: default avatarZach O'Keefe <zokeefe@google.com>
Reviewed-by: default avatarYang Shi <shy828301@gmail.com>
Cc: Alex Shi <alex.shi@linux.alibaba.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Chris Kennelly <ckennelly@google.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Helge Deller <deller@gmx.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Pavel Begunkov <asml.silence@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Cc: "Souptick Joarder (HPE)" <jrdr.linux@gmail.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
parent 50ad2f24

mm/khugepaged.c

+58 −25
Original line number Diff line number Diff line
@@ -73,6 +73,8 @@ static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait); 
 * default collapse hugepages if there is at least one pte mapped like

 * it would have happened if the vma was large enough during page

 * fault.

 *

 * Note that these are only respected if collapse was initiated by khugepaged.

 */

static unsigned int khugepaged_max_ptes_none __read_mostly;

static unsigned int khugepaged_max_ptes_swap __read_mostly;
@@ -86,6 +88,8 @@ static struct kmem_cache *mm_slot_cache __read_mostly; 
#define MAX_PTE_MAPPED_THP 8



struct collapse_control {

	bool is_khugepaged;



	/* Num pages scanned per node */

	u32 node_load[MAX_NUMNODES];
@@ -554,6 +558,7 @@ static bool is_refcount_suitable(struct page *page) 
static int __collapse_huge_page_isolate(struct vm_area_struct *vma,

					unsigned long address,

					pte_t *pte,

					struct collapse_control *cc,

					struct list_head *compound_pagelist)

{

	struct page *page = NULL;
@@ -566,8 +571,10 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, 
		pte_t pteval = *_pte;

		if (pte_none(pteval) || (pte_present(pteval) &&

				is_zero_pfn(pte_pfn(pteval)))) {

			++none_or_zero;

			if (!userfaultfd_armed(vma) &&

			    ++none_or_zero <= khugepaged_max_ptes_none) {

			    (!cc->is_khugepaged ||

			     none_or_zero <= khugepaged_max_ptes_none)) {

				continue;

			} else {

				result = SCAN_EXCEED_NONE_PTE;
@@ -587,12 +594,15 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, 


		VM_BUG_ON_PAGE(!PageAnon(page), page);



		if (page_mapcount(page) > 1 &&

				++shared > khugepaged_max_ptes_shared) {

		if (page_mapcount(page) > 1) {

			++shared;

			if (cc->is_khugepaged &&

			    shared > khugepaged_max_ptes_shared) {

				result = SCAN_EXCEED_SHARED_PTE;

				count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);

				goto out;

			}

		}



		if (PageCompound(page)) {

			struct page *p;
@@ -654,10 +664,14 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, 
		if (PageCompound(page))

			list_add_tail(&page->lru, compound_pagelist);

next:

		/* There should be enough young pte to collapse the page */

		if (pte_young(pteval) ||

		    page_is_young(page) || PageReferenced(page) ||

		    mmu_notifier_test_young(vma->vm_mm, address))

		/*

		 * If collapse was initiated by khugepaged, check that there is

		 * enough young pte to justify collapsing the page

		 */

		if (cc->is_khugepaged &&

		    (pte_young(pteval) || page_is_young(page) ||

		     PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm,

								     address)))

			referenced++;



		if (pte_write(pteval))
@@ -666,7 +680,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, 


	if (unlikely(!writable)) {

		result = SCAN_PAGE_RO;

	} else if (unlikely(!referenced)) {

	} else if (unlikely(cc->is_khugepaged && !referenced)) {

		result = SCAN_LACK_REFERENCED_PAGE;

	} else {

		result = SCAN_SUCCEED;
@@ -745,6 +759,7 @@ static void khugepaged_alloc_sleep(void) 




struct collapse_control khugepaged_collapse_control = {

	.is_khugepaged = true,

	.last_target_node = NUMA_NO_NODE,

};
@@ -1025,7 +1040,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, 
	mmu_notifier_invalidate_range_end(&range);



	spin_lock(pte_ptl);

	result =  __collapse_huge_page_isolate(vma, address, pte,

	result =  __collapse_huge_page_isolate(vma, address, pte, cc,

					       &compound_pagelist);

	spin_unlock(pte_ptl);
@@ -1116,7 +1131,9 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma, 
	     _pte++, _address += PAGE_SIZE) {

		pte_t pteval = *_pte;

		if (is_swap_pte(pteval)) {

			if (++unmapped <= khugepaged_max_ptes_swap) {

			++unmapped;

			if (!cc->is_khugepaged ||

			    unmapped <= khugepaged_max_ptes_swap) {

				/*

				 * Always be strict with uffd-wp

				 * enabled swap entries.  Please see
@@ -1134,8 +1151,10 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma, 
			}

		}

		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {

			++none_or_zero;

			if (!userfaultfd_armed(vma) &&

			    ++none_or_zero <= khugepaged_max_ptes_none) {

			    (!cc->is_khugepaged ||

			     none_or_zero <= khugepaged_max_ptes_none)) {

				continue;

			} else {

				result = SCAN_EXCEED_NONE_PTE;
@@ -1165,12 +1184,15 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma, 
			goto out_unmap;

		}



		if (page_mapcount(page) > 1 &&

				++shared > khugepaged_max_ptes_shared) {

		if (page_mapcount(page) > 1) {

			++shared;

			if (cc->is_khugepaged &&

			    shared > khugepaged_max_ptes_shared) {

				result = SCAN_EXCEED_SHARED_PTE;

				count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);

				goto out_unmap;

			}

		}



		page = compound_head(page);
@@ -1220,14 +1242,22 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma, 
			result = SCAN_PAGE_COUNT;

			goto out_unmap;

		}

		if (pte_young(pteval) ||

		    page_is_young(page) || PageReferenced(page) ||

		    mmu_notifier_test_young(vma->vm_mm, address))



		/*

		 * If collapse was initiated by khugepaged, check that there is

		 * enough young pte to justify collapsing the page

		 */

		if (cc->is_khugepaged &&

		    (pte_young(pteval) || page_is_young(page) ||

		     PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm,

								     address)))

			referenced++;

	}

	if (!writable) {

		result = SCAN_PAGE_RO;

	} else if (!referenced || (unmapped && referenced < HPAGE_PMD_NR/2)) {

	} else if (cc->is_khugepaged &&

		   (!referenced ||

		    (unmapped && referenced < HPAGE_PMD_NR / 2))) {

		result = SCAN_LACK_REFERENCED_PAGE;

	} else {

		result = SCAN_SUCCEED;
@@ -1896,7 +1926,9 @@ static int khugepaged_scan_file(struct mm_struct *mm, struct file *file, 
			continue;



		if (xa_is_value(page)) {

			if (++swap > khugepaged_max_ptes_swap) {

			++swap;

			if (cc->is_khugepaged &&

			    swap > khugepaged_max_ptes_swap) {

				result = SCAN_EXCEED_SWAP_PTE;

				count_vm_event(THP_SCAN_EXCEED_SWAP_PTE);

				break;
@@ -1947,7 +1979,8 @@ static int khugepaged_scan_file(struct mm_struct *mm, struct file *file, 
	rcu_read_unlock();



	if (result == SCAN_SUCCEED) {

		if (present < HPAGE_PMD_NR - khugepaged_max_ptes_none) {

		if (cc->is_khugepaged &&

		    present < HPAGE_PMD_NR - khugepaged_max_ptes_none) {

			result = SCAN_EXCEED_NONE_PTE;

			count_vm_event(THP_SCAN_EXCEED_NONE_PTE);

		} else {